Training in progress, step 28, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671466706
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e9420f6f3fc29633a07c26c966bcb335bdc2f001c1272653d3ea778f90fe75f
|
3 |
size 671466706
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3af919c555bec5b3888603008190cf11cf4bd7bea96f8db9233e3b5826dcd798
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43e032ef089020d5839ac578e9f697942b93e6f5e70ffa2f2e4ef22911f2f3bc
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0150c85cacd33a934780e6948dff1a6d8ed9a4be406087fb780c11d9e9c7811c
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5918b22653fdb96197b377b737ccda1244b18ac02e12732ec0b9ce22d350d8fa
|
3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5d68508636586630def15adada56bacf5564430dadc7cdc60a1b731c838c499
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -198,6 +198,27 @@
|
|
198 |
"eval_samples_per_second": 15.47,
|
199 |
"eval_steps_per_second": 4.022,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +242,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos":
|
230 |
"train_batch_size": 2,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 3.0684931506849313,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 28,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 15.47,
|
199 |
"eval_steps_per_second": 4.022,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.8493150684931505,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 1.130761821582766e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.958904109589041,
|
211 |
+
"grad_norm": NaN,
|
212 |
+
"learning_rate": 1.0328100665587574e-05,
|
213 |
+
"loss": 0.0,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 3.0684931506849313,
|
218 |
+
"grad_norm": NaN,
|
219 |
+
"learning_rate": 1e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 28
|
222 |
}
|
223 |
],
|
224 |
"logging_steps": 1,
|
|
|
242 |
"should_evaluate": false,
|
243 |
"should_log": false,
|
244 |
"should_save": true,
|
245 |
+
"should_training_stop": true
|
246 |
},
|
247 |
"attributes": {}
|
248 |
}
|
249 |
},
|
250 |
+
"total_flos": 3.342126825697444e+17,
|
251 |
"train_batch_size": 2,
|
252 |
"trial_name": null,
|
253 |
"trial_params": null
|